]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/discovery.py
885944c5e8bf95e7af78c5c3ed4eb5f69cc7a35f
[youtubedl] / youtube_dl / extractor / discovery.py
1 from __future__ import unicode_literals
2
3 import re
4 import json
5
6 from .common import InfoExtractor
7
8
9 class DiscoveryIE(InfoExtractor):
10 _VALID_URL = r'http://dsc\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
11 _TEST = {
12 'url': 'http://dsc.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
13 'file': '614784.mp4',
14 'md5': 'e12614f9ee303a6ccef415cb0793eba2',
15 'info_dict': {
16 'title': 'MythBusters: Mission Impossible Outtakes',
17 'description': ('Watch Jamie Hyneman and Adam Savage practice being'
18 ' each other -- to the point of confusing Jamie\'s dog -- and '
19 'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
20 ' back.'),
21 'duration': 156,
22 },
23 }
24
25 def _real_extract(self, url):
26 mobj = re.match(self._VALID_URL, url)
27 video_id = mobj.group('id')
28 webpage = self._download_webpage(url, video_id)
29
30 video_list_json = self._search_regex(r'var videoListJSON = ({.*?});',
31 webpage, 'video list', flags=re.DOTALL)
32 video_list = json.loads(video_list_json)
33 info = video_list['clips'][0]
34 formats = []
35 for f in info['mp4']:
36 formats.append(
37 {'url': f['src'], r'ext': r'mp4', 'tbr': int(f['bitrate'][:-1])})
38
39 return {
40 'id': info['contentId'],
41 'title': video_list['name'],
42 'formats': formats,
43 'description': info['videoCaption'],
44 'thumbnail': info.get('videoStillURL') or info.get('thumbnailURL'),
45 'duration': info['duration'],
46 }